Vidu S2
Vidu S2 is Shengshu's real-time interactive video generation model, the successor to Vidu S1. It combines two components: Vidu S2-Avatar for real-time 720p digital character generation with dynamic reference updates and instruction following like dancing, and Vidu S2-Editing for live video stream editing including style transfer, clothing replacement, character replacement, and background replacement.
- Type
- Video
- Weights
- Closed
More from ShengShu Technology
10
-
MotuBrain
Multimodal
MotuBrain is ShengShu Technology’s world action model for embodied robotics. It is built as a universal brain…
-
Vidu 2.0
Video
Next generation Vidu model with improved physics, longer sequences, and tighter style control.
-
Vidu Q2
Video
Vidu Q2 is an upgraded text and image to video model. It delivers sharper detail, steadier motion, stronger i…
-
Vidu Q2 Pro
Video
Premium Q2 profile with maximum temporal stability and micro detail.
-
Vidu Q2 Turbo
Video
Speed tuned Q2 variant for rapid drafts and cost efficient iteration.
-
Vidu Q3
Multimodal
Vidu Q3 is ShengShu Technology’s long-form AI video model that generates a single 16-second clip with native,…
-
Vidu S1
Video
Vidu S1 is a real time interactive video generation model for voice controlled digital characters. Users uplo…
About ShengShu Technology
1
ShengShu develops multimodal foundation and world models, including the Vidu AI video-generation platform.